Transformer-based approaches have gained significant attention in image restoration, where the core component, i.e, Multi-Head Attention (MHA), plays a crucial role in capturing diverse features and recovering high-quality results. In MHA, heads perform attention calculation independently from uniform split subspaces, and a redundancy issue is triggered to hinder the model from achieving satisfactory outputs. In this paper, we propose to improve MHA by exploring diverse learners and introducing various interactions between heads, which results in a Hierarchical multI-head atteNtion driven Transformer model, termed HINT, for image restoration. HINT contains two modules, i.e., the Hierarchical Multi-Head Attention (HMHA) and the Query-Key Cache Updating (QKCU) module, to address the redundancy problem that is rooted in vanilla MHA. Specifically, HMHA extracts diverse contextual features by employing heads to learn from subspaces of varying sizes and containing different information. Moreover, QKCU, comprising intra- and inter-layer schemes, further reduces the redundancy problem by facilitating enhanced interactions between attention heads within and across layers. Extensive experiments are conducted on 12 benchmarks across 5 image restoration tasks, including low-light enhancement, dehazing, desnowing, denoising, and deraining, to demonstrate the superiority of HINT. The source code is available in the supplementary materials.

In the domain of intelligent driving, enhancing the precision of integrated positioning systems remains a critical challenge. The Kalman filter (KF) is a widely adopted approach to address this issue. However, the traditional Kalman filter using linear model and fixed noise model will affect the estimation accuracy of the system. To address the shortcomings of the traditional Kalman filter in integrated positioning systems, this paper proposes an adaptive extended Kalman filter (AEKF). The AEKF uses the covariance matching principle (CMP) and singular spectrum analysis (SSA) to enhance the accuracy and reliability of positioning systems. It integrates laser inertial odometer (LIO) and real-time kinematic (RTK) technologies. The AEKF based on CMP and SSA is called CMP-SSA-AEKF in this paper. The CMP-SSA-AEKF can adaptively update the process noise covariance matrix and the measurement noise covariance matrix in parallel. It overcomes linearization errors, enhances environmental adaptability, and does not incur significant computational costs. Through comparative analysis, this study tests the CMP-SSA-AEKF, as well as the Extended Kalman filter (EKF) and the Unscented Kalman filter (UKF), using multiple experimental metrics. The results show that the CMP-SSA-AEKF is superior to the conventional EKF and UKF in positioning accuracy and stability.

Emotion inference in multi-turn conversations aims to predict the participant's emotion in the next upcoming turn without knowing the participant's response yet, and is a necessary step for applications such as dialogue planning.However, it is a severe challenge to perceive and reason about the future feelings of participants, due to the lack of utterance information from the future.Moreover, it is crucial for emotion inference to capture the characteristics of emotional propagation in conversations, such as persistence and contagiousness.In this study, we focus on investigating the task of emotion inference in multi-turn conversations by modeling the propagation of emotional states among participants in the conversation history, and propose an addresseeaware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn.In addition, we propose an ensemble strategy to further enhance the model performance.Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines.